Model save

README.md

@@ -27,7 +27,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/gongc1995-city-university-of-hong-kong/huggingface/runs/nut4sim8) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/gongc1995-city-university-of-hong-kong/huggingface/runs/o7bd1r7p) 
 
 
 This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.023221049398088302,
-    "train_runtime": 8217.2755,
+    "train_loss": 0.0,
+    "train_runtime": 1.4449,
     "train_samples": 7500,
-    "train_samples_per_second": 0.913,
-    "train_steps_per_second": 0.009
+    "train_samples_per_second": 5190.534,
+    "train_steps_per_second": 53.982
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
-size 11422063
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.023221049398088302,
-    "train_runtime": 8217.2755,
+    "train_loss": 0.0,
+    "train_runtime": 1.4449,
     "train_samples": 7500,
-    "train_samples_per_second": 0.913,
-    "train_steps_per_second": 0.009
+    "train_samples_per_second": 5190.534,
+    "train_steps_per_second": 53.982
 }

trainer_state.json

@@ -234,21 +234,13 @@
       "step": 75
     },
     {
-      "clip_ratio": 0.0,
-      "completion_length": 630.8084576924642,
       "epoch": 0.9984,
-      "kl": 0.040715535481770836,
-      "reward": 2.5170717736085257,
-      "reward_std": 0.3583106442044179,
-      "rewards/accuracy_reward": 0.5885416728754839,
-      "rewards/format_reward": 0.9496527860562006,
-      "rewards/tag_count_reward": 0.978877325852712,
       "step": 78,
       "total_flos": 0.0,
-      "train_loss": 0.023221049398088302,
-      "train_runtime": 8217.2755,
-      "train_samples_per_second": 0.913,
-      "train_steps_per_second": 0.009
+      "train_loss": 0.0,
+      "train_runtime": 1.4449,
+      "train_samples_per_second": 5190.534,
+      "train_steps_per_second": 53.982
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b65b8e440af6e4afb6a0a99aa6f8d28439c0c031a0a4bb6ff17a78eefebde30
+oid sha256:7cfe0f8538cc4c42e2129f52a6782b03291044e7fb8546567700784af60ecc28
 size 8056